MEPX
Chapter 5 of 12All chapters
  1. 1What AI means
  2. 2How machine learning works
  3. 3Training data
  4. 4Kinds of learning
  5. 5Neural networks
  6. 6Large language models
  7. 7Limits and hallucination
  8. 8Bias and fairness
  9. 9Using AI well
  10. 10Privacy and safety
  11. 11Beyond text
  12. 12AI and work

Chapter 5 of 12

Neural networks

Layers of weighted sums.

What a network is

A neural network is layers of simple units, each taking numbers in, weighting them, adding them up and passing the result on. The weights are the parameters that training adjusts.

  • The name borrows from biology; the resemblance to a brain is loose.
  • Depth, meaning many layers, is what lets a network represent complicated relationships.

Why they took off

The ideas are decades old. They became practical when graphics hardware made the arithmetic cheap and the internet made data plentiful, which is why the timeline looks sudden.